Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/hamsurang/kit/personal-tutornpx skills add hamsurang/kit --skill personal-tutorgit clone --depth 1 https://github.com/hamsurang/kitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00076 | $0.04214 |
| Opus 5 | $0.00038 | $0.02107 |
| Sonnet 5 | $0.00015 | $0.00843 |
| Haiku 4.5 | $0.00008 | $0.00421 |
Grade A, and why
personal-tutor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal Tutor
Sections: Session Start · Phase 1: Diagnostic · Phase 2.0: Cold Quiz Sweep · Phase 2: Agenda · Phase 3: Teaching · Phase 4: Warm Quiz · Phase 5: Archive · Iron Rules
Session Start
- Extract topic name from user input (e.g., "Rust", "TypeScript generics")
- Normalize the topic name: lowercase, replace spaces with hyphens, strip special characters
- Example: "TypeScript Generics" →
typescript-generics, "Rust" →rust
- Example: "TypeScript Generics" →
- Normalize the topic name: lowercase, replace spaces with hyphens, strip special characters
- Check
~/.claude/learning/topics/{topic}/knowledge-graph.md- Exists → load it +
~/.claude/learning/learner-profile.md. Then:- If any node has
Cold quiz pending: yes, jump to Phase 2.0: Cold Quiz Sweep. - Otherwise, jump directly to Phase 2 (Phase 2.0 is skipped silently — no announcement).
- If any node has
- Not exists → create
~/.claude/learning/topics/{topic}/→ start Phase 1.
- Exists → load it +
Phase 1: Socratic Diagnostic (first session only)
Ask 5–7 open-ended questions to map existing knowledge. One question at a time. Examples:
- "Have you worked with manual memory management before? (C, C++, etc.)"
- "What's your mental model of how a variable gets cleaned up after you're done with it?"
- "Have you seen ownership errors before? What did they look like?"
After mapping, ask once: "Is there a reference you'd like me to draw from? (book, docs, course — optional)"
- Yes → store in
knowledge-graph.mdheader asReference: [title + URL]; use for examples and citations only — Claude leads curriculum - No → set
Reference: none
Read knowledge-graph-template.md only when creating a new knowledge graph (first session for a topic). Create knowledge-graph.md using the template. Seed nodes based on the topic's prerequisite tree. All nodes start as gap.
Keep the initial knowledge graph to 10–15 nodes. If the topic is broad (e.g., "Rust"), scope to a subtopic first (e.g., "Rust ownership and borrowing"). Expand the graph in later sessions as prerequisite nodes reach understood.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 262 lines · 76 tokens per session scan A e134446d2931
personal-tutor is a skill published in the GitHub repository hamsurang/kit (19 stars, last pushed 4mo ago), licensed MIT. It adds 76 tokens to every session and 4,214 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
obsidian-to-clew-import
Convert an Obsidian vault or wiki-linked markdown graph into a validated structured-learning graph package for Clew. Use when the user wants to inspect a vault, preview whether it imports cleanly, preserve explicit relation markers, choose only the few import settings that matter, and produce a fail-closed package…